Hongning Wang

The Conversational Artificial Intelligence (CoAI) Group, Tsinghua University

Tsinghua AI

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Eval Frameworks & Benchmarks (1)RLHF & Preference Learning (1)

Frequent co-authors

Bosi Wen (1)Bosi Wen (1)Yilin Niu (1)Yilin Niu (1)

Papers (1)

Mar 5, 2026

Tsinghua AI1w ago·also Westlake, Zhipu

IF-RewardBench: Benchmarking Judge Models for Instruction-Following Evaluation

Current judge models for instruction-following are surprisingly unreliable, but a new benchmark exposes their flaws and offers a path to better alignment.

Bosi Wen, Bosi Wen, Yilin Niu +12

Eval Frameworks & Benchmarks RLHF & Preference Learning

Search

Hongning Wang

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)